A novel neuroscience-inspired architecture: for computer vision applications

The theory behind deep learning, the human visual system was investigated and general principles of how it functions are extracted. Our finding is that there are neuroscience theories that are not utilized in deep learning. Therefore, in this work, a novel model utilizing some of those theories...

Full description

Bibliographic Details
Main Authors: Hassan, Marwa Yousif, Khalifa, Othman Omran, Abu Talib, Azhar, Olanrewaju, Rashidah Funke, Hassan Abdalla Hashim, Aisha
Format: Proceeding Paper
Language:English
English
Published: Institute of Electrical and Electronic Engineers 2016
Subjects:
Online Access:http://irep.iium.edu.my/50466/
http://irep.iium.edu.my/50466/1/50466_A_novel_neuroscience-inspired_architecture.pdf
http://irep.iium.edu.my/50466/4/50466_A%20novel%20neuroscience_scopus.pdf
_version_ 1848783650250817536
author Hassan, Marwa Yousif
Khalifa, Othman Omran
Abu Talib, Azhar
Olanrewaju, Rashidah Funke
Hassan Abdalla Hashim, Aisha
author_facet Hassan, Marwa Yousif
Khalifa, Othman Omran
Abu Talib, Azhar
Olanrewaju, Rashidah Funke
Hassan Abdalla Hashim, Aisha
author_sort Hassan, Marwa Yousif
building IIUM Repository
collection Online Access
description The theory behind deep learning, the human visual system was investigated and general principles of how it functions are extracted. Our finding is that there are neuroscience theories that are not utilized in deep learning. Therefore, in this work, a novel model utilizing some of those theories is developed. The new model addresses the parallel nature of the human brain compared to the hierarchal (serial) brain model that is followed by current deep learning systems. The validation of the proposed model was conducted using “Shape” feature dimension. The results show up to 2% accuracy rate compared to our implementation of DeepFace, a high performing face recognition algorithm that was developed by Facebook, is achieved under the same hardware/ software conditions; and we were able to speed up the training up to 21% per a training patch compared to DeepFace.
first_indexed 2025-11-14T16:24:43Z
format Proceeding Paper
id iium-50466
institution International Islamic University Malaysia
institution_category Local University
language English
English
last_indexed 2025-11-14T16:24:43Z
publishDate 2016
publisher Institute of Electrical and Electronic Engineers
recordtype eprints
repository_type Digital Repository
spelling iium-504662017-01-03T08:03:15Z http://irep.iium.edu.my/50466/ A novel neuroscience-inspired architecture: for computer vision applications Hassan, Marwa Yousif Khalifa, Othman Omran Abu Talib, Azhar Olanrewaju, Rashidah Funke Hassan Abdalla Hashim, Aisha T10.5 Communication of technical information The theory behind deep learning, the human visual system was investigated and general principles of how it functions are extracted. Our finding is that there are neuroscience theories that are not utilized in deep learning. Therefore, in this work, a novel model utilizing some of those theories is developed. The new model addresses the parallel nature of the human brain compared to the hierarchal (serial) brain model that is followed by current deep learning systems. The validation of the proposed model was conducted using “Shape” feature dimension. The results show up to 2% accuracy rate compared to our implementation of DeepFace, a high performing face recognition algorithm that was developed by Facebook, is achieved under the same hardware/ software conditions; and we were able to speed up the training up to 21% per a training patch compared to DeepFace. Institute of Electrical and Electronic Engineers 2016 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/50466/1/50466_A_novel_neuroscience-inspired_architecture.pdf application/pdf en http://irep.iium.edu.my/50466/4/50466_A%20novel%20neuroscience_scopus.pdf Hassan, Marwa Yousif and Khalifa, Othman Omran and Abu Talib, Azhar and Olanrewaju, Rashidah Funke and Hassan Abdalla Hashim, Aisha (2016) A novel neuroscience-inspired architecture: for computer vision applications. In: 2016 Conference of Basic Sciences and Engineering Studies (SGCAC), 20th-23rd Feb. 2016, Gam’aa Street, Khartoum, Sudan. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7458013&tag=1 10.1109/SGCAC.2016.7458013
spellingShingle T10.5 Communication of technical information
Hassan, Marwa Yousif
Khalifa, Othman Omran
Abu Talib, Azhar
Olanrewaju, Rashidah Funke
Hassan Abdalla Hashim, Aisha
A novel neuroscience-inspired architecture: for computer vision applications
title A novel neuroscience-inspired architecture: for computer vision applications
title_full A novel neuroscience-inspired architecture: for computer vision applications
title_fullStr A novel neuroscience-inspired architecture: for computer vision applications
title_full_unstemmed A novel neuroscience-inspired architecture: for computer vision applications
title_short A novel neuroscience-inspired architecture: for computer vision applications
title_sort novel neuroscience-inspired architecture: for computer vision applications
topic T10.5 Communication of technical information
url http://irep.iium.edu.my/50466/
http://irep.iium.edu.my/50466/
http://irep.iium.edu.my/50466/
http://irep.iium.edu.my/50466/1/50466_A_novel_neuroscience-inspired_architecture.pdf
http://irep.iium.edu.my/50466/4/50466_A%20novel%20neuroscience_scopus.pdf